IBM/ACPBench
ACPBench: Reasoning about Action, Change, and Planning. A benchmark designed to evaluate the fundamental reasoning abilities in the domains of action, change, and planning. It spans seven atomic reasoning tasks--determining action applicability, action reachability, plan justification, determining landmark, predicting state transitions, state rea
This project helps evaluate how well AI models understand and reason about real-world tasks involving sequences of actions, changes in environment, and planning. It takes in descriptions of a problem (like moving cars with a ferry) and asks questions about applicable actions, predictable outcomes, or whether a goal is achievable. The output is a performance score for the AI's reasoning abilities. It's designed for AI researchers and developers creating or assessing advanced AI systems.
Use this if you are developing or evaluating large language models or other AI agents that need to perform complex reasoning, planning, and decision-making in dynamic environments.
Not ideal if you are looking for a ready-to-use AI planning system or a tool to solve specific real-world operational problems directly, as this is a benchmark for AI capabilities.
Stars
32
Forks
5
Language
Python
License
—
Category
Last pushed
Feb 11, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/IBM/ACPBench"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
sierra-research/tau2-bench
τ²-Bench: Evaluating Conversational Agents in a Dual-Control Environment
xlang-ai/OSWorld
[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
bigcode-project/bigcodebench
[ICLR'25] BigCodeBench: Benchmarking Code Generation Towards AGI
scicode-bench/SciCode
A benchmark that challenges language models to code solutions for scientific problems
THUDM/AgentBench
A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)